ayushi-agarwal commented on a change in pull request #30334: URL: https://github.com/apache/spark/pull/30334#discussion_r546236723
########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/UnionEstimation.scala ########## @@ -0,0 +1,97 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.sql.catalyst.plans.logical.statsEstimation + +import scala.collection.mutable.ArrayBuffer + +import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeMap} +import org.apache.spark.sql.catalyst.plans.logical.{ColumnStat, Statistics, Union} +import org.apache.spark.sql.types.{ByteType, DataType, DateType, DecimalType, DoubleType, FloatType, IntegerType, LongType, ShortType, TimestampType} + +/** + * Estimate the number of output rows by doing the sum of output rows for each child of union, + * and estimate min and max stats for each column by finding the overall min and max of that + * column coming from its children. + */ +object UnionEstimation { + import EstimationUtils._ + + def compare(a: Any, b: Any, dataType: DataType): Boolean = { + dataType match { + case dt: IntegerType => dt.ordering.asInstanceOf[Ordering[Any]].lt(a, b) + case dt: LongType => dt.ordering.asInstanceOf[Ordering[Any]].lt(a, b) + case dt: FloatType => dt.ordering.asInstanceOf[Ordering[Any]].lt(a, b) + case dt: DoubleType => dt.ordering.asInstanceOf[Ordering[Any]].lt(a, b) + case dt: ShortType => dt.ordering.asInstanceOf[Ordering[Any]].lt(a, b) + case dt: ByteType => dt.ordering.asInstanceOf[Ordering[Any]].lt(a, b) + case dt: DateType => dt.ordering.asInstanceOf[Ordering[Any]].lt(a, b) + case dt: TimestampType => dt.ordering.asInstanceOf[Ordering[Any]].lt(a, b) + case dt: DecimalType => dt.ordering.asInstanceOf[Ordering[Any]].lt(a, b) Review comment: Added a comparator ########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/UnionEstimation.scala ########## @@ -0,0 +1,97 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.sql.catalyst.plans.logical.statsEstimation + +import scala.collection.mutable.ArrayBuffer + +import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeMap} +import org.apache.spark.sql.catalyst.plans.logical.{ColumnStat, Statistics, Union} +import org.apache.spark.sql.types.{ByteType, DataType, DateType, DecimalType, DoubleType, FloatType, IntegerType, LongType, ShortType, TimestampType} + +/** + * Estimate the number of output rows by doing the sum of output rows for each child of union, + * and estimate min and max stats for each column by finding the overall min and max of that + * column coming from its children. + */ +object UnionEstimation { + import EstimationUtils._ + + def compare(a: Any, b: Any, dataType: DataType): Boolean = { Review comment: Changed ########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/UnionEstimation.scala ########## @@ -0,0 +1,97 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.sql.catalyst.plans.logical.statsEstimation + +import scala.collection.mutable.ArrayBuffer + +import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeMap} +import org.apache.spark.sql.catalyst.plans.logical.{ColumnStat, Statistics, Union} +import org.apache.spark.sql.types.{ByteType, DataType, DateType, DecimalType, DoubleType, FloatType, IntegerType, LongType, ShortType, TimestampType} Review comment: Changed ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
